Institution
Hangzhou Dianzi University
Education•Hangzhou, China•
About: Hangzhou Dianzi University is a education organization based out in Hangzhou, China. It is known for research contribution in the topics: Computer science & Control theory. The organization has 14547 authors who have published 14941 publications receiving 144766 citations. The organization is also known as: Hangzhou Institute of Electrical Engineering & Hángzhōu diànzǐ kējì dàxué.
Topics: Computer science, Control theory, Nonlinear system, Artificial neural network, Feature extraction
Papers published on a yearly basis
Papers
More filters
••
TL;DR: It is found that performance expectancy, task technology fit, social influence, and facilitating conditions have significant effects on user adoption and the unified theory of acceptance and usage of technology (UTAUT) model is integrated.
1,245 citations
••
TL;DR: In this paper, the authors present a review of coal fly ash at the global level, focusing on its current and potential applications, including use in the soil amelioration, construction industry, ceramic industry, catalysis, depth separation, zeolite synthesis, etc.
1,167 citations
••
TL;DR: An attribute-person recognition (APR) network is proposed, a multi-task network which learns a re-ID embedding and at the same time predicts pedestrian attributes, and demonstrates that by learning a more discriminative representation, APR achieves competitive re-IDs performance compared with the state-of-the-art methods.
762 citations
••
01 Jan 2013TL;DR: Drawing on the information systems success model and flow theory, this research identified the factors affecting continuance intention of mobile payment and indicated that servicequality is the main factor affecting trust, whereas system quality is themain factor affecting satisfaction.
Abstract: Retaining users and facilitating their continuance usage are crucial for mobile payment service providers. Drawing on the information systems success model and flow theory, this research identified the factors affecting continuance intention of mobile payment. We conducted data analysis with structural equation modeling. The results indicated that service quality is the main factor affecting trust, whereas system quality is the main factor affecting satisfaction. Information quality and service quality affect flow. Trust, flow and satisfaction determine continuance intention of mobile payment. The results imply that service providers need to offer quality system, information and services in order to facilitate users' continuance usage of mobile payment. Highlights? Service quality is the main factor affecting trust. ? System quality is the main factor affecting satisfaction. ? Information quality and service quality affect flow. ? Trust, flow and satisfaction determine continuance usage of mobile payment.
657 citations
••
04 Aug 2017
TL;DR: A Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multi- modal features, which results in superior performance for VQA compared with other bilinear pooling approaches.
Abstract: Visual question answering (VQA) is challenging because it requires a simultaneous understanding of both the visual content of images and the textual content of questions. The approaches used to represent the images and questions in a fine-grained manner and questions and to fuse these multimodal features play key roles in performance. Bilinear pooling based models have been shown to outperform traditional linear models for VQA, but their high-dimensional representations and high computational complexity may seriously limit their applicability in practice. For multimodal feature fusion, here we develop a Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multi-modal features, which results in superior performance for VQA compared with other bilinear pooling approaches. For fine-grained image and question representation, we develop a ‘co-attention’ mechanism using an end-to-end deep network architecture to jointly learn both the image and question attentions. Combining the proposed MFB approach with co-attention learning in a new network architecture provides a unified model for VQA. Our experimental results demonstrate that the single MFB with co-attention model achieves new state-of-theart performance on the real-world VQA dataset. Code available at https://github.com/yuzcccc/mfb.
581 citations
Authors
Showing all 14669 results
Name | H-index | Papers | Citations |
---|---|---|---|
Jian Zhang | 107 | 3064 | 69715 |
Andrzej Cichocki | 97 | 952 | 41471 |
Qing-Long Han | 97 | 537 | 28970 |
Brian D. O. Anderson | 96 | 1107 | 47104 |
Zhigang Zou | 92 | 727 | 37378 |
Tamer Basar | 88 | 977 | 34903 |
Yong Xu | 88 | 1391 | 39268 |
Xiaoping Hu | 85 | 450 | 24291 |
Gang Feng | 82 | 611 | 26012 |
Xiang-Yang Li | 77 | 632 | 22509 |
Jiashi Feng | 77 | 426 | 21521 |
Zhen Wang | 75 | 758 | 28991 |
Xiao Dong Chen | 73 | 1513 | 30188 |
Chin-Chen Chang | 69 | 1205 | 22366 |
Xin Liu | 69 | 885 | 19231 |